Tsui-Wei Weng

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability CVPR 2026 Interpretable and Steerable Concept Bottleneck Sparse Autoencoders CVPR 2026 Concept Bottleneck Large Language Models ICLR 2025 Effective Skill Unlearning through Intervention and Abstention NAACL 2025 Evaluating Neuron Explanations: A Unified Framework with Sanity Checks ICML 2025 Interpretable Generative Models through Post-hoc Concept Bottlenecks CVPR 2025 Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities NAACL 2025 SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness WACV 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Understanding Fixed Predictions via Confined Regions ICML 2025 Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification NeurIPS 2024 AND: Audio Network Dissection for Interpreting Deep Acoustic Models ICML 2024 Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents ICML 2024 Interpretability-Guided Test-Time Adversarial Defense ECCV 2024 Linear Explanations for Individual Neurons ICML 2024 Prediction without Preclusion: Recourse Verification with Reachable Sets ICLR 2024 Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data NeurIPS 2024 Provable and Efficient Dataset Distillation for Kernel Ridge Regression NeurIPS 2024 Provably Robust Conformal Prediction with Improved Efficiency ICLR 2024 VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance NeurIPS 2024 CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks ICLR 2023 ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction ICML 2023 Corrupting Neuron Explanations of Deep Visual Features ICCV 2023 Label-free Concept Bottleneck Models ICLR 2023 Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning ICLR 2023 Adversarially Robust Conformal Prediction ICLR 2022 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning ICLR 2021 On the Equivalence between Neural Network and Support Vector Machine NeurIPS 2021 Robust Deep Reinforcement Learning through Adversarial Loss NeurIPS 2021 Higher-Order Certification For Randomized Smoothing NeurIPS 2020 Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control ICLR 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks AAAI 2019 Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective IJCAI 2019 Efficient Neural Network Robustness Certification with General Activation Functions NeurIPS 2018